INDEX

Explanations

terms related to Indian Pale Ales (IPAs) in the context of beer and brewing

oai_token-act-pair · gpt-3.5-turbo

types of beer, particularly IPAs and ales

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Telecommunications

-0.82

aido

-0.81

 Neuroscience

-0.76

bilt

-0.73

 Telecom

-0.73

MpServer

-0.70

aldo

-0.69

operated

-0.69

MRI

-0.68

romy

-0.67

POSITIVE LOGITS

 brewed

1.30

 flavored

0.96

 brewing

0.89

 brewer

0.88

 conco

0.88

 brew

0.84

 flavour

0.84

 tasting

0.84

IPA

0.83

 poppy

0.82

Activations Density 0.020%

terms related to Indian Pale Ales (IPAs) in the context of beer and brewing

types of beer, particularly IPAs and ales

No Comments

No Known Activations